Perplexity · Model Gateway API

Perplexity Orchestrator API

Perplexity has launched the Orchestrator API, a hosted inference gateway that serves frontier models from OpenAI, Anthropic, Google and xAI, plus open-weight models such as GLM, Kimi and DeepSeek, behind one base URL. It accepts OpenAI Chat Completions, OpenAI Responses and Anthropic Messages requests, and fails over between providers for the same model. A routing preview (perplexity/auto) selects models by route descriptions, and on a 63-task Terminal-Bench 4.1 subset Perplexity self-reports a rise from 38/63 to 41/63 tasks when refusal routes are added. Each request is billed at the answering model's published rate with no extra platform fee on credits.

Open the source ↗

Similar Developer Tools releases

More from Perplexity

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.